Advances and Applications in Statistics
Volume 18, Issue 2, Pages 175 - 188
(October 2010)
|
|
MAXIMUM LIKELIHOOD AND BAYESIAN ESTIMATION IN A SOFTWARE RELIABILITY MODEL WITH EXPONENTIAL FAULT CORRECTION TIME
K. Harishchandra and K. M. Manjunatha
|
Abstract: During the past three decades, numerous statistical models have been proposed for estimating software reliability (Lyu [5] and Pham [6]). Most of the software reliability models deal with the fault detection processes and fault correction times are ignored. In this paper, we propose a software reliability model taking into account the fault correction time. The software failure times as well as correction times are assumed to be exponential. The model is formulated as two-state Markov processes, state ‘0’ the software fault detection phase and state ‘1’ the fault correction phase. The maximum likelihood estimators and Bayesian estimators of the software reliability model parameters are obtained. A large sample test for the model parameters is also discussed. |
Keywords and phrases: software reliability, fault detection state, fault correction state, maximum likelihood estimation, Bayesian estimation, large sample test. |
Communicated by Shaul K. Bar-Lev |
Number of Downloads: 380 | Number of Views: 1370 |
|